© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84758
    Prev
    Next
    INDEX
    Explanations

    text following quotation marks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     new
    -1.78
     their
    -1.68
    ⦑
    -1.61
     Each
    -1.58
     Several
    -1.54
     Since
    -1.53
     Some
    -1.53
     Every
    -1.51
     Despite
    -1.45
     Although
    -1.43
    POSITIVE LOGITS
    崀
    1.44
    鶫
    1.31
    菒
    1.29
     definiert
    1.27
     Hidro
    1.26
    probably
    1.25
    ebly
    1.21
    comme
    1.21
    ¥
    1.21
    prende
    1.20
    Activations Density 0.014%

    No Known Activations